Exploring Factors that Contribute to Country Development
Education and the World: Literacy rates, Human Development Index, and their relationship
You can include links using Markdown syntax as shown.
You should include links to relevant sites as you write. You should additionally include a list of references as the end of your blog with full citations (and relevant links).
“The Human Development Index (HDI) is a summary measure of average achievement in key dimensions of human development: a long and healthy life, being knowledgeable and having a decent standard of living. The HDI is the geometric mean of normalized indices for each of the three dimensions.” -UN Development Program
In the world map below, countries are colored according to their Human Development Index score. Each country is assigned an HDI score-a number between 0 and 1, designed, in a rough sense, to measure quality of life. Notice that countries further from the equator are more likely to have a high HDI score than countries closer to the equator. This trend shows up as a visual gradient on the map: the further from the equator, the higher the HDI score, the more blue the countries appear. But this is not a general rule. The term “Gloabl South” is often used to describe a collection of so-called “under-developed” countries near the equator and south of it, a collection which the map below suggests.
However, his map is quite one dimensional. Just what exactly does HDI tell us? What, in concrete terms, does “human development” mean? The goal of the following analysis is to shed light on HDI through other measures, in particular those related to expected years of education, literacy rates, population density, and women’s empowerment.
Education
HDI vs. Expected Years of Education
Education is widely considered to have a strong contribution to the advancements of societies and the quality of life of the people who live in them. In the definition of the HDI measurement mentioned above, being knowledgeable is a contributing factor to a country’s HDI value. Curious to see how the length of time spent in school affects the UN’s measure of knowledge and a country’s HDI, we plotted countries’ HDI vs expected years of schooling to observe the trend between the two.
## `geom_smooth()` using formula 'y ~ x'
Note: The points that belong to the NA continent group are countries
that were unsuccessfully matched with a continent during the data
wrangling process.
The linear regression of the plotted points has an \(R^2\) of 0.802, supporting the assumption of a strong correlation between the two variables. However, there are clearly some other factors that must influence the HDI as we can see that Europe has more countries plotted over the regression while Africa has more countries plotted below the regression. Although we know the main factors that are used to measure HDI, these results point towards regional variables influencing of HDI (could be issues accessing resources, emigration, etc.). In the future, we’d be curious to explore what the issues common issues among the countries below the regression and common accomplishments among countries above the regression.
Chloropleth Comparison
Below, we’ve included chloropleths of the expected years of education and HDI so they can be compared side by side. These chloropleths help the countries that are plotted further from the regression stand out because their more drastic change in shade from one graph to the other compared to some of the other countries’ more nuanced changes.
Education
HDI
Literacy Rate and HDI
We begin our inquiry into HDI and education by asking: Which is a better predictor of literacy rates - HDI, or average number of years of education? More over, what does it mean if HDI predicts literacy rates better than average number of years of education?
For each country, we can find an expected number of years of schooling; this is the number of years the average student attends school. In countries where the average years of schooling is higher, we expect to find higher average literacy rates.
For each continent, we calculated two correlation coefficient. First, we found the correlation between HDI score and literacy rate; in other words, how well does HDI predict literacy rate for that continent. Second, we found the correlation between average years of education and literacy rate; in other words, how well does years of schooling predict literacy rate for that continent.
Next, for each continent, we found the difference between these two correlations. The interesting results are those where this difference is small. A small difference in these two values means that “development” is as good a predictor of literacy rates as years of education. A small difference indicates that non-educational “developmental” factors are influencing literacy rates.
Observe that two continents, South America and Africa, are picked out as
having a smaller difference. This means that in these two continents,
extra educational factors are influencing literacy rates. This
observation tracks with the delineation into “Global South” and “Global
North” indicated by the plot of HDI. That is, the literacy rates of
South America and Africa, continents situated in the Global South,
suffer from extra-educational factors.
One problem with this analysis is that it is not granular. It gives us a view of the world that is split into seven, when in reality, the world has far more than seven borders.
Our next analysis clusters countries according to literacy rate and population density. The goal of the analysis is to show that the division into Global North and Global South is inadequate to understand differences in literacy rates. In other words, the delineation into North and South indicated by HDI is a simplification - the actual situation is more complicated.
Before this analysis can proceed, we first make an observation about the relationship between population density and literacy rates. Compare the plots of Population Density vs. Literacy Rate, and Log of Population Density vs. Literacy Rate. Observe that a line of best fit on the first plot would be exponential, while in the second, a line of best fit would be linear. This suggests that for the purposes of clustering, it would be appropriate to cluster Log of Population Density against Literacy Rate.
The elbow plot shows that a cluster analysis using three clusters is most appropriate. The plot below associates each country with one of three clusters. The first cluster, 1, consists of countries with high literacy rate and low population density. The second cluster, 2, consists of countries with high literacy rate and high density. The third cluster, 3, consists of countries with low literacy rate. Notice that this third cluster ranges over a wide variety of population densities.
## # A tibble: 3 x 5
## latestRate_scaled density_scaled size withinss cluster
## <dbl> <dbl> <int> <dbl> <fct>
## 1 0.412 -1.07 47 25.9 1
## 2 -1.77 -0.150 33 42.1 2
## 3 0.432 0.612 90 54.4 3
The following map colors each country according to its cluster
assignment. What is interesting about this map is that it shows how
groups of contiguous countries are likely to fall into the same cluster.
What does this mean? As an example, examine the pair of North African
countries Algeria and Libya. These two countries are near the equator,
and in our previous analysis, were part of the group described as the
Global South. Here however, we can see that Algeria and Libya belong to
a collection of countries with high literacy rate.
Visualizations
Visualizations, particularly interactive ones, will be well-received. That said, do not overuse visualizations. You may be better off with one complicated but well-crafted visualization as opposed to many quick-and-dirty plots. Any plots should be well-thought-out, properly labeled, informative, and visually appealing.
If you want to include dynamic visualizations or tables, you should explore your options from packages that are built from htmlwidgets. These htmlwidgets-based packages offer ways to build lighterweight, dynamic visualizations or tables that don’t require an R server to run! A more complete list of packages is available on the linked website, but a short list includes:
- plotly: Interactive graphics with D3
- leaflet: Interactive maps with OpenStreetMap
- dygraphs: Interactive time series visualization
- visNetwork: Network graph visualization vis.js
- sparkline: Small inline charts
- threejs: Interactive 3D graphics
You may embed a published Shiny app in your blog if useful, but be aware that there is a limited window size for embedded objects, which tends to makes the user experience of the app worse relative to a dedicated Shiny app page. Additionally, Shiny apps will go idle after a few minutes and have to be reloaded by the user, which may also affect the user experience.
Any Shiny apps embedded in your blog should be accompanied by the link to the published Shiny app (I did this using a figure caption in the code chunk below, but you don’t have to incorporate the link in this way).
Tables
DT package
The DT package is great for making dynamic tables that can be displayed, searched, and filtered by the user without needing an R server or Shiny app!
Note: you should load any packages you use in the setup
code chunk as usual. The library() functions are shown
below just for demonstration.
library(DT)## Warning: package 'DT' was built under R version 4.1.2
mtcars %>%
select(mpg, cyl, hp) %>%
datatable(colnames = c("MPG", "Number of cylinders", "Horsepower"),
filter = 'top',
options = list(pageLength = 10, autoWidth = TRUE))kableExtra package
You can also use kableExtra for customizing HTML tables.
library(kableExtra)
summary(cars) %>%
kbl(col.names = c("Speed", "Distance"),
row.names = FALSE) %>%
kable_styling(bootstrap_options = "striped",
full_width = FALSE) %>%
row_spec(0, bold = TRUE) %>%
column_spec(1:2, width = "1.5in") | Speed | Distance |
|---|---|
| Min. : 4.0 | Min. : 2.00 |
| 1st Qu.:12.0 | 1st Qu.: 26.00 |
| Median :15.0 | Median : 36.00 |
| Mean :15.4 | Mean : 42.98 |
| 3rd Qu.:19.0 | 3rd Qu.: 56.00 |
| Max. :25.0 | Max. :120.00 |
Images
Images and gifs can be displayed using code chunks:
“Safe Space” by artist Kenesha Sneed
This is a figure caption
You may also use Markdown syntax for displaying images as shown below, but code chunks offer easier customization of the image size and alignment.